INDEX

Explanations

keywords and terms related to functionality and usability in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Following "Category:" or list-related words

np_acts-logits-general · gemini-2.0-flash

Eton College, fat, issues, cache, world

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Мексичка

-1.23

 незавершена

-1.19

^(@)

-1.18

 NSCoder

-1.17

`,

-1.15

 ་་

-1.13

 consultato

-1.13

存于互联网档案馆

-1.11

 للمعارف

-1.07

 CreateTagHelper

-1.06

POSITIVE LOGITS

↵↵

2.10

<eos>

1.94

↵↵↵

1.69

↵

1.50

↵↵↵↵

1.36

↵↵↵↵↵

1.24

↵↵↵↵↵↵↵

1.02

↵↵↵↵↵↵

1.00

</h2>

0.95

↵↵↵↵↵↵↵↵

0.92

Activations Density 3.317%

keywords and terms related to functionality and usability in various contexts

Following "Category:" or list-related words

Eton College, fat, issues, cache, world

No Comments

No Known Activations